init_project

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations present, the description carries the full disclosure burden and performs well: 'Non-destructive and idempotent' states the safety profile, and it names exactly what side effects occur (creates primer/ store, modifies CLAUDE.md, conditionally AGENTS.md). This is precisely the kind of behavioral context annotations would otherwise provide. Minor gap: no mention of what is returned on completion, though an output schema exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences, zero filler. The purpose and concrete effects come first, safety follows, then the one-time ordering constraint, then the optional-parameter guidance. Every sentence carries distinct information, and the most critical scoping constraint ('before any other tool') is prominently placed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a project-initialization tool with no annotations and an output schema to cover return values, the description covers everything needed: what gets created or modified, idempotency/safety, the once-and-first invocation rule, and when to supply the optional parameter. Nothing an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It does explain jira_project_key's conditional purpose ('if tickets may later be exported to Jira'), which is genuinely additive beyond the schema's bare 'Jira Project Key' title. However, project_name receives no semantic treatment beyond its schema title 'Project Name', which is trivial but still undocumented at the description level. Partial compensation only.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource ('Initialise this project for primer-mcp') followed by concrete actions: 'creates the primer/ ticket store and adds the workflow section to CLAUDE.md (and AGENTS.md if it exists)'. This clearly differentiates it from all 16 siblings, which are ticket lifecycle and planning operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit usage context: 'Call this once per project, before any other tool.' It states the ordering constraint relative to every sibling tool, and the jira_project_key line adds a conditional-use guideline. It does not name specific alternatives or when-not conditions, but given that the sibling list contains only post-initialization tools, the intended usage is unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.